Skip to main content

Table 1 AUC table for ROC analysis

From: Combining gene prediction methods to improve metagenomic gene annotation

Method

AUC (%)

GM

78.2

MGA

71.4

Orph

69.2

GM & Orph

85.9

Consensus

81.1

GM|MGA|Orph

65.5

  1. The area under the curve for each method for the receiver-operatoring characteristic (ROC) curves, constructed by varying the read-length. GeneMark has the best AUC for a single-method while GM & Orphelia has the best performance for the combination methods, with the consensus combination trailing by a few percentage.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us